ResearchBenchmarksCollect on Collect Stochastic OriginalCollect on Collect Stochastic OriginalFollow8.11Average RewardVPN7.52767.67887.837.9812Jul 11, 2017Evaluation resultsMethodMethodLinksAverage RewardVPNplanning steps=5planning steps=52017.078.11DQN2017.077.85VPNplanning steps=1planning steps=12017.077.84Shortest2017.077.64Greedy2017.077.58OPNplanning steps=5planning steps=52017.077.55